OpenRouter 模型 ↗ · 2026-09-19
prism-ml/ternary-bonsai-2-27b
Model release OpenRouter 模型 Source language: Chinese
OpenRouter 于 2026-09-19 收录该模型(收录时间不等于模型正式发布日期);上下文:262,144 tokens;输入价:$0.0750/百万 tokens;输出价:$0.5000/百万 tokens;定位(来源描述):Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B.
Full text
PrismML: Ternary Bonsai 2 27B
prism-ml/ternary-bonsai-2-27b
Model weights
Compare
Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks the language-model weights to roughly 8.5 GB while retaining 98.2% of the base model's average score across PrismML's 14 thinking-mode benchmarks, enabling efficient inference on consumer hardware. The model thinks by default and defaults to xhigh reasoning effort.
Modalities
In / out price
$0.075 / $0.50per 1M
Context
262K
Released
Sep 18, 2026
Compare
Providers
This model is hosted by one provider. OpenRouter forwards every request without routing.
Latency / throughput
$0.075$0.50$0.03750.53s32 tok/s
98.14%
ProviderInput / Output /M
Input $0.075 / Output $0.50
32 tok/s98.14% uptime
Pricing
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Weighted average
Input
$0.07188/M tokens
Output
$0.4972/M tokens
Ternary Bonsai 2 27B — Price history
Price history
No effective price data for this selection
$0.0719$0.4970.0%100.0%
ProviderInput / Output /M
Token share
Effective in $0.0719 / Effective out $0.497
Token share
100.0%
Performance
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Throughput
32tok/s
P50, best across providers
Latency
0.53s
P50, best provider
Reasoning effort
Uptime
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Uptime (3d)The model was reachable. Request routed to a provider.
100.00%
Availability (3d)The model returned inference from any provider. Errors and empty responses count against it.
99.32%
Availability over the last 3 days
Last 72 hours
Availability 99.32%
3 Days Ago2 Days AgoYesterdayNow
Availability over the last 24 hours
OpenRouter Availability
98.69%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and provider routing options.
Apps
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
1.
Raises.com
new
41.5Mtokens
2.
Hermes Agent
Hermes Agent is an open-source, self-improving AI agent by Nous Research that runs persistently with memory across sessions, and builds reusable skills from experience. It comes with 40+ built-in tools, including web search, browser automation, and vision, plus scheduled automations and subagents.
26.1Mtokens
3.
Nous Research API
Nous Research is an AI research team focused on advancing open-source AI.
4.88Mtokens
4.
Realm Intelligence (titanensemble)
new
2.99Mtokens
5.
Hello Haven
new
2.69Mtokens
Rest of OpenRouter
18K
Top 5 Apps
0
Activity
Token volume and request traffic to this model over time.
API
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
Not currently available through EU in-region routing. In-region routing docs
Frequently asked questions
Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token context window. Ternary compression shrinks the language-model weights to roughly 8.5 GB while retaining 98.2% of the base model's average score across PrismML's 14 thinking-mode benchmarks, enabling efficient inference...
Ternary Bonsai 2 27B costs $0.075/M input tokens and $0.50/M output tokens, with separate rates for Cache Read at $0.0375/M tokens.
Ternary Bonsai 2 27B has a 262,144 token context window. It supports up to 32,768 completion tokens.
Yes. Ternary Bonsai 2 27B accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
Ternary Bonsai 2 27B accepts text and images as input and returns text.
Ternary Bonsai 2 27B is served by 1 provider on OpenRouter: Darkbloom.
Ternary Bonsai 2 9B is another text model from PrismML.
Ternary Bonsai 2 27B was released on September 18, 2026.